Related papers: Robust Semantic Interpretability: Revisiting Conce…
Visual prompt tuning offers significant advantages for adapting pre-trained visual foundation models to specific tasks. However, current research provides limited insight into the interpretability of this approach, which is essential for…
Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients. However, two challenges arise when deploying deep learning models to real-world…
In the context of image classification, Concept Bottleneck Models (CBMs) first embed images into a set of human-understandable concepts, followed by an intrinsically interpretable classifier that predicts labels based on these intermediate…
Decision processes of computer vision models - especially deep neural networks - are opaque in nature, meaning that these decisions cannot be understood by humans. Thus, over the last years, many methods to provide human-understandable…
Deep learning methods have become very popular for the processing of natural images, and were then successfully adapted to the neuroimaging field. As these methods are non-transparent, interpretability methods are needed to validate them…
Reinforcement Learning (RL) can enable agents to learn complex tasks. However, it is difficult to interpret the knowledge and reuse it across tasks. Inductive biases can address such issues by explicitly providing generic yet useful…
Saliency methods provide post-hoc model interpretation by attributing input features to the model outputs. Current methods mainly achieve this using a single input sample, thereby failing to answer input-independent inquiries about the…
The increasing impact of black box models, and particularly of unsupervised ones, comes with an increasing interest in tools to understand and interpret them. In this paper, we consider in particular how to characterise visual groupings…
Recent breakthroughs in NLP research, such as the advent of Transformer models have indisputably contributed to major advancements in several tasks. However, few works research robustness and explainability issues of their evaluation…
Recent years have seen a growing interest in methods for predicting an unknown variable of interest, such as a subject's diagnosis, from medical images depicting its anatomical-functional effects. Methods based on discriminative modeling…
As AI technology is increasingly applied to high-impact, high-risk domains, there have been a number of new methods aimed at making AI models more human interpretable. Despite the recent growth of interpretability work, there is a lack of…
Concept-based interpretability methods aim to explain deep neural network model predictions using a predefined set of semantic concepts. These methods evaluate a trained model on a new, "probe" dataset and correlate model predictions with…
As large language models are increasingly trained and fine-tuned, practitioners need methods to identify which training data drive specific behaviors, particularly unintended ones. Training Data Attribution (TDA) methods address this by…
With the rapid growth of text-to-image models, a variety of techniques have been suggested to prevent undesirable image generations. Yet, these methods often only protect against specific user prompts and have been shown to allow unsafe…
Recent developments in machine learning have introduced models that approach human performance at the cost of increased architectural complexity. Efforts to make the rationales behind the models' predictions transparent have inspired an…
Machine learning models use high dimensional feature spaces to map their inputs to the corresponding class labels. However, these features often do not have a one-to-one correspondence with physical concepts understandable by humans, which…
Recurrent Neural Networks (RNNs) are often used for sequential modeling of adverse outcomes in electronic health records (EHRs) due to their ability to encode past clinical states. These deep, recurrent architectures have displayed…
Developing inherently interpretable models for prediction has gained prominence in recent years. A subclass of these models, wherein the interpretable network relies on learning high-level concepts, are valued because of closeness of…
Interpreting the inner function of neural networks is crucial for the trustworthy development and deployment of these black-box models. Prior interpretability methods focus on correlation-based measures to attribute model decisions to…
One of the significant challenges of deep neural networks is that the complex nature of the network prevents human comprehension of the outcome of the network. Consequently, the applicability of complex machine learning models is limited in…